RTX 5090 local inference for Llama

[fastbench]

My first guess would be this: On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[thetapath]

What worked for me was pretty simple. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious.

[fusedhall]

Not sure I agree there. I've seen people blame consumer GPUs when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one.

[circuitwire58]

My first guess would be this: If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.